Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    forcing Bias

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appliquée
    0.42
    UTONIUM
    0.41
     desple
    0.40
    陂
    0.40
     исте
    0.39
    墠
    0.39
     Tried
    0.38
    til
    0.38
    ALLY
    0.38
    poi
    0.38
    POSITIVE LOGITS
     uppercase
    0.40
    犇
    0.40
    कृष्ट
    0.38
     subtleties
    0.36
     glfw
    0.36
    ❸
    0.36
     propane
    0.35
     elegante
    0.35
    Beautiful
    0.35
    гар
    0.35
    Act Density 0.000%

    No Known Activations